基於自監督預訓練與孿生網路架構的指紋辨識方法

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：21

、訪客IP：3.141.7.31

姓名

壽柏安(Po-An Shou) 查詢紙本館藏

畢業系所

資訊工程學系

論文名稱

基於自監督預訓練與孿生網路架構的指紋辨識方法
(Research on Fingerprint Recognition Method Based on Self-supervised Pre-training and Siamese Network Architecture)

相關論文

★ Single and Multi-Label Environmental Sound Recognition with Gaussian Process	★ 波束形成與音訊前處理之嵌入式系統實現
★ 語音合成及語者轉換之應用與設計	★ 基於語意之輿情分析系統
★ 高品質口述系統之設計與應用	★ 深度學習及加速強健特徵之CT影像跟骨骨折辨識及偵測
★ 基於風格向量空間之個性化協同過濾服裝推薦系統	★ RetinaNet應用於人臉偵測
★ 金融商品走勢預測	★ 整合深度學習方法預測年齡以及衰老基因之研究
★ 漢語之端到端語音合成研究	★ 基於 ARM 架構上的 ORB-SLAM2 的應用與改進
★ 基於深度學習之指數股票型基金趨勢預測	★ 探討財經新聞與金融趨勢的相關性
★ 基於卷積神經網路的情緒語音分析	★ 運用深度學習方法預測阿茲海默症惡化與腦中風手術存活

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

至系統瀏覽論文 ( 永不開放)

摘要(中)

本研究針對指紋辨識領域中資料稀缺性與應用場景多樣化的挑戰，提出一套基於自監督預訓練與孿生網路架構的指紋辨識方法，以提升模型的準確性與穩健性。指紋辨識作為身份認證的重要技術，已廣泛應用於支付系統、安全管理及個人裝置等領域。然而，由於公開指紋資料集的數量有限且多為標準化樣本，難以涵蓋實際應用中的複雜場景，如指紋部分缺損、噪聲干擾與跨感測器變化等問題，使得模型在應用中的效能受限。私有資料集的隱私性與保密性更進一步限制了訓練數據的獲取，成為當前指紋辨識研究面臨的重要瓶頸。
為了解決上述問題，本研究首先採用自監督學習技術，通過對比學習與預訓練，充分挖掘未標記指紋資料中的潛在特徵，為模型提供強大的初始化，減少對標記資料的依賴。接著，設計孿生網路架構，利用兩個共享參數的預訓練子網路對指紋影像進行特徵提取，並通過歐幾里得距離計算影像間的相似性。此架構能有效應對部分缺損、噪聲干擾及跨感測器變化等挑戰場景，提升辨識效能。本研究結果顯示，提出的方法在指紋資料集上的辨識效能達到良好效果，預訓練模型使下游微調可以更快速收斂，節省訓練資源與時間，且在處理複雜場景的指紋時展現出高度的穩健性與泛化能力。

摘要(英)

This study addresses the challenges of data scarcity and the diverse application scenarios in the field of fingerprint recognition by proposing a fingerprint recognition method based on self-supervised pretraining and a Siamese network architecture. This method aims to improve the accuracy and robustness of the model. As an essential technology for identity authentication, fingerprint recognition has been widely applied in payment systems, security management, and personal devices. However, the limited availability of public fingerprint datasets, which are predominantly standardized samples, fails to adequately cover the complex scenarios encountered in real-world applications, such as partial fingerprint degradation, noise interference, and cross-sensor variations. Consequently, the performance of models in practical applications is restricted. Moreover, the privacy and confidentiality of proprietary datasets further limit access to training data, representing a critical bottleneck in current fingerprint recognition research.
To address these challenges, this study first employs self-supervised learning techniques to fully explore the latent features in unlabeled fingerprint data through contrastive learning and pretraining. This approach provides a robust initialization for the model and reduces dependency on labeled data. Subsequently, a Siamese network architecture is designed, where two pretrained subnetworks with shared parameters are used to extract features from fingerprint images. The similarity between images is calculated using the Euclidean distance. This architecture effectively tackles challenging scenarios such as partial degradation, noise interference, and cross-sensor variations, thereby enhancing recognition performance.
The experimental results demonstrate that the proposed method achieves satisfactory recognition performance on fingerprint datasets. The pretrained model enables faster convergence during downstream fine-tuning, saving training resources and time. Furthermore, it exhibits high robustness and generalization capabilities when processing fingerprints in complex scenarios.

關鍵字(中)

★ 自監督學習
★ 孿生網路架構

關鍵字(英)

★ Self-Supervised Learning
★ Siamese Neural Networks

論文目次

中文摘要 i
Abstract ii
圖目錄 vi
表目錄 vii
第一章緒論 1
1.1 背景 1
1.2 研究動機與目的 3
1.3 研究方法與章節概要 3
第二章文獻探討 5
2.1 卷積神經網路Convolutional neural network 5
2.1.1. 殘差神經網路 ResNet 6
2.2 自監督學習Self-Supervised Learning 8
2.2.1. Barlow Twins 9
2.2.2. Barlow Twins 預訓練方法 10
2.3 Spatial Transformer Networks 12
2.3.1. Localization Network 定位網絡 13
2.3.2. Grid Generator 網格生成器 13
2.3.3. Sampler採樣器 14
2.4 Siamese Neural Networks孿生神經網路 15
第三章基於自監督預訓練與孿生網路架構的指紋辨識方法 17
3.1 數據預處理 18
3.1.1. 平場校正 Flat-field Correction (FFC) 18
3.1.2. 基於低通濾波與梯度差異的影像紋理增強 19
3.1.3. 數據預處理流程 20
3.2 自監督骨幹網路預訓練 22
3.3 孿生網路架構微調 24
第四章實驗結果與討論 26
4.1 實驗設備 26
4.2 訓練資料集 27
4.2.1. PrintsGAN 27
4.2.2. Innolux Dataset 28
4.3 實驗結果 29
4.3.1. Barlows Twins Pretrain訓練結果 29
4.3.2. 下游任務微調實驗結果 31
4.3.3. 消融實驗 32
第五章結論及未來方向 35
第六章參考文獻 36

參考文獻

[1] Vaswani, A. (2017). Attention is all you need. Advances in Neural Information Processing Systems.
[2] Takahashi, A., Koda, Y., Ito, K., & Aoki, T. (2020, September). Fingerprint feature extraction by combining texture, minutiae, and frequency spectrum using multi-task CNN. In 2020 IEEE international joint conference on biometrics (IJCB) (pp. 1-8). IEEE.
[3] Grosz, S. A., & Jain, A. K. (2023). Afr-net: Attention-driven fingerprint recognition network. IEEE Transactions on Biometrics, Behavior, and Identity Science.
[4] https://www.image-net.org/challenges/LSVRC/
[5] Krizhevsky, A. (2014). One weird trick for parallelizing convolutional neural networks. arXiv preprint arXiv:1404.5997.
[6] Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
[7] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
[8] Koch, G., Zemel, R., & Salakhutdinov, R. (2015, July). Siamese neural networks for one-shot image recognition. In ICML deep learning workshop (Vol. 2, No. 1, pp. 1-30).
[9] Hoffer, E., & Ailon, N. (2015). Deep metric learning using triplet network. In Similarity-based pattern recognition: third international workshop, SIMBAD 2015, Copenhagen, Denmark, October 12-14, 2015. Proceedings 3 (pp. 84-92). Springer International Publishing.
[10] Howard, A. G. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861.
[11] Tan, M., & Le, Q. (2019, May). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning (pp. 6105-6114). PMLR.
[12] Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., ... & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 10012-10022).
[13] Jaderberg, M., Simonyan, K., & Zisserman, A. (2015). Spatial transformer networks. Advances in neural information processing systems, 28.
[14] LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324.
[15] Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4700-4708).
[16] Tan, M., & Le, Q. (2019, May). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning (pp. 6105-6114). PMLR.
[17] Devlin, J. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
[18] Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020, November). A simple framework for contrastive learning of visual representations. In International conference on machine learning (pp. 1597-1607). PMLR.
[19] He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 9729-9738).
[20] Grill, J. B., Strub, F., Altche, F., Tallec, C., Richemond, P., Buchatskaya, E., ... & Valko, M. (2020). Bootstrap your own latent-a new approach to self-supervised learning. Advances in neural information processing systems, 33, 21271-21284.
[21] Zbontar, J., Jing, L., Misra, I., LeCun, Y., & Deny, S. (2021, July). Barlow twins: Self-supervised learning via redundancy reduction. In International conference on machine learning (pp. 12310-12320). PMLR.
[22] FastEnhanceTexture. https://github.com/luannd/MinutiaeNet/blob/master/CoarseNet/MinutiaeNet_utils.py.
[23] Engelsma, J. J., Grosz, S., & Jain, A. K. (2022). Printsgan: Synthetic fingerprint generator. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(5), 6111-6124.

指導教授

王家慶(Jia-Ching Wang)

審核日期

2025-1-22

推文